Techniques for Deduplicated Data Access Statistics Management

1. A method for data access statistics management comprising: determining, using at least one computer processor, that a portion of data of a plurality of portions of data has been deduplicated by receiving an indication that the plurality of portions of data are going to be deduplicated into a deduplicated portion of data; combining access statistics for the plurality of portions of data by incrementing access statistics associated with the deduplicated portion of data to indicate an additional write request for each additional reference to the portion of data contained in an access statistic associated with a deduplicated instance of the deduplicated portion of data, wherein the access statistics comprise a weighted average, and wherein each additional reference indicates that a duplicate block was not written to storage; and associating the combined access statistics with the deduplicated portion of data.

2. The method of claim 1 , wherein the access statistics provide an indication of at least one of Input/Output (I/O) temperature and a access time.

3. The method of claim 1 , wherein the access statistics provide an indication of Input/Output (I/O) temperature, and wherein the Input/Output (I/O) temperature is used to perform at least one of: determining which portions of data to pre-fetch into cache memory; and determining which portions of data to store in higher performance storage.

4. The method of claim 3 , wherein higher performance storage comprises at least one of: storage with faster access times; storage with faster seek times; and storage spread across multiple disks.

5. The method of claim 1 , wherein the portion of data comprises a block.

6. The method of claim 1 , wherein the portion of data comprises a segment.

7. The method of claim 1 , further comprising: detecting a reference being added to the deduplicated portion of data; and incrementing the access count of the deduplicated portion of data for the reference.

8. At least one non-transitory processor readable non-transitory storage medium for storing a computer program of instructions configured to be readable by at least one processor for instructing the at least one processor to execute a computer process for performing the method as recited in claim 1 .

9. An article of manufacture for data access statistics management, the article of manufacture comprising: at least one non-transitory processor readable medium; and instructions stored on the at least one medium; wherein the instructions are configured to be readable from the at least one medium by at least one processor and thereby cause the at least one processor to operate so as to: determine that a portion of data of a plurality of portions of data has been deduplicated by receiving an indication that a plurality of portions of data are going to be deduplicated into a deduplicated portion of data; combine access statistics for the plurality of portions of data by incrementing access statistics associated with the deduplicated portion of data to indicate an additional write request for each additional reference to the portion of data contained in an access statistic associated with a deduplicated instance of the deduplicated portion of data, wherein the access statistics comprise a weighted average, and wherein each additional reference indicates that a duplicate block was not written to storage; and associate the combined access statistics with the deduplicated portion of data.

10. The article of manufacture of claim 9 , wherein the access statistics are to perform at least one of: determining which portions of data to pre-fetch into cache memory; and determining which portions of data to store in higher performance storage.

11. The article of manufacture of claim 9 , wherein the access statistics are used to determine which portions of data to store in higher performance storage, and wherein higher performance storage comprises at least one of: storage with faster access times; storage with faster seek times; and storage spread across multiple disks.

12. The article of manufacture of claim 9 , wherein the portion of data comprises a block.

13. The article of manufacture of claim 9 , wherein the portion of data comprises a segment.

14. The article of manufacture of claim 9 , wherein the instructions are configured to further cause the processor to: detect a reference being added to the deduplicated portion of data; and increment the access count of the deduplicated portion of data for the reference.

15. A system for data access statistics management comprising: one or more processors communicatively coupled to a network; wherein the one or more processors are configured to: determine that a portion of data of a plurality of portions of data has been deduplicated by receiving an indication that a plurality of portions of data are going to be deduplicated into a deduplicated portion of data; combine access statistics for the plurality of portions of data by incrementing access statistics associated with the deduplicated portion of data to indicate an additional write request for each additional reference to the portion of data contained in an access statistic associated with a deduplicated instance of the deduplicated portion of data, wherein the access statistics comprise a weighted average, and wherein each additional reference indicates that a duplicate block was not written to storage; and associate the combined access statistics with the deduplicated portion of data.

16. The system of claim 15 , wherein the access statistics provide an indication of at least one of Input/Output (I/O) temperature and an access time.

17. The system of claim 15 , wherein the access statistics provide an indication of Input/Output (I/O) temperature, and wherein the Input/Output (I/O) temperature is used to perform at least one of: determining which portions of data to pre-fetch into cache memory; and determining which portions of data to store in higher performance storage.